open-llm-leaderboard/details_Josephgflowers__Tinyllama-1.5B-Cinder-Test-5
收藏数据集概述
数据集创建背景
该数据集是在评估模型 Josephgflowers/Tinyllama-1.5B-Cinder-Test-5 的过程中自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建，每个运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Josephgflowers__Tinyllama-1.5B-Cinder-Test-5", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-07T14:16:10.337681 运行的最新结果：
python { "all": { "acc": 0.24463011554499428, "acc_stderr": 0.03029810764251703, "acc_norm": 0.2458345840613761, "acc_norm_stderr": 0.031099024034521226, "mc1": 0.2558139534883721, "mc1_stderr": 0.01527417621928336, "mc2": 0.404111232343749, "mc2_stderr": 0.014795822821048516 }, "harness|arc:challenge|25": { "acc": 0.28668941979522183, "acc_stderr": 0.013214986329274788, "acc_norm": 0.3250853242320819, "acc_norm_stderr": 0.013688147309729122 }, "harness|hellaswag|10": { "acc": 0.3881696873132842, "acc_stderr": 0.00486337569815387, "acc_norm": 0.49432383987253536, "acc_norm_stderr": 0.004989459871609184 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614866, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.29056603773584905, "acc_stderr": 0.02794321998933714, "acc_norm": 0.29056603773584905, "acc_norm_stderr": 0.02794321998933714 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.25, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.04158307533083286, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.04158307533083286 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20425531914893616, "acc_stderr": 0.02635515841334941, "acc_norm": 0.20425531914893616, "acc_norm_stderr": 0.02635515841334941 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.20175438596491227, "acc_stderr": 0.037752050135836386, "acc_norm": 0.20175438596491227, "acc_norm_stderr": 0.037752050135836386 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924812, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924812 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.022569897074918417, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.022569897074918417 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.036196045241242515, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.036196045241242515 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23548387096774193, "acc_stderr": 0.02413763242933771, "acc_norm": 0.23548387096774193, "acc_norm_stderr": 0.02413763242933771 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.030712730070982592, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.030712730070982592 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.18, "acc_stderr": 0.03861229196653697, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653697 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24242424242424243, "acc_stderr": 0.03346409881055953, "acc_norm": 0.24242424242424243, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.18181818181818182, "acc_stderr": 0.027479603010538787, "acc_norm": 0.18181818181818182, "acc_norm_stderr": 0.027479603010538787 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.03027690994517826, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.03027690994517826 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.18717948717948718, "acc_stderr": 0.019776601086550036, "acc_norm": 0.18717948717948718, "acc_norm_stderr": 0.019776601086550036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.0263357394040558, "acc_norm": 0.248148148148148
